Unsupervised LiDAR-Based Multi-UAV Detection and Tracking Under Extreme Sparsity

2026-03-12

AI Summary

This work addresses the challenge of robust multi-UAV perception under extremely sparse LiDAR observations, where small aerial vehicles generate only 1–2 points per frame in non-repetitive scanning scenarios—rendering conventional detection and multi-object tracking methods ineffective. The authors propose an unsupervised, LiDAR-only detection and tracking pipeline that integrates range-adaptive DBSCAN clustering, a three-stage temporal consistency verification, joint probabilistic data association (JPDA) for data linking, and interacting multiple model (IMM) filtering. This approach achieves reliable tracking even at the perceptual limit of 1–2 points per frame, quantified here for the first time without labeled data. Experimental results demonstrate that JPDA significantly reduces identity switches by 64% in trajectory-crossing scenarios. Real-world flight tests yield a precision of 0.891, recall of 0.804, and RMSE of 0.63 meters, while simulations show near-perfect MOTA performance.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

Non-repetitive solid-state LiDAR scanning leads to an extremely sparse measurement regime for detecting airborne UAVs: a small quadrotor at 10-25 m typically produces only 1-2 returns per scan, which is far below the point densities assumed by most existing detection approaches and inadequate for robust multi-target data association. We introduce an unsupervised, LiDAR-only pipeline that addresses both detection and tracking without the need for labeled training data. The detector integrates range-adaptive DBSCAN clustering with a three-stage temporal consistency check and is benchmarked on real-world air-to-air flight data under eight different parameter configurations. The best setup attains 0.891 precision, 0.804 recall, and 0.63 m RMSE, and a systematic minPts sweep verifies that most scans contain at most 1-2 target points, directly quantifying the sparsity regime. For multi-target tracking, we compare deterministic Hungarian assignment with joint probabilistic data association (JPDA), each coupled with Interacting Multiple Model filtering, in four simulated scenarios with increasing levels of ambiguity. JPDA cuts identity switches by 64% with negligible impact on MOTA, demonstrating that probabilistic association is advantageous when UAV trajectories approach one another closely. A two-environment evaluation strategy, combining real-world detection with RTK-GPS ground truth and simulation-based tracking with identity-annotated ground truth, overcomes the limitations of GNSS-only evaluation at inter-UAV distances below 2 m.

Problem

• LiDAR
• UAV detection
• extreme sparsity
• multi-target tracking
• data association

Innovation

• extreme sparsity
• unsupervised LiDAR
• multi-UAV tracking
• JPDA
• temporal consistency